Screen recording video-based information verification method and device, equipment and storage medium

Abstract

The application relates to an artificial intelligence technology and discloses an information verification method based on a screen recording video, which comprises the following steps: obtaining a screen recording video during information collection; converting the screen recording video into a video frame sequence sorted by time; classifying each video frame in the video frame sequence by using a pre-trained lightweight neural network to obtain a key video frame sequence; performing operation scene identification on the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence; and performing information verification on the screen recording video according to the operation scene sequence. The application further discloses an information verification device based on a screen recording video, an electronic device and a storage medium. The application can improve the correctness of user information filling.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to an information verification method and device based on a screen recording video, an electronic device, and a computer readable storage medium. BACKGROUND

[0002] Obtaining the credit situation of a user is an important part of the financial industry, and usually requires cooperation with a third-party credit investigation agency to obtain the credit information of the user, but this requires strict control of the risk control of the third-party credit investigation agency, and data that the third-party credit investigation agency does not have also needs to be filled in and submitted by the user.

[0003] Currently, the user fills in the information by himself or uploads the information that needs to be uploaded by himself through screenshots, but neither of these two methods can take evidence of the process of uploading the user information, so the accuracy and authenticity of the information cannot be guaranteed, resulting in incorrect user information and low accuracy of the obtained user credit information. SUMMARY

[0004] The present application provides an information verification method and device based on a screen recording video and a computer readable storage medium, which mainly aims to solve the problem of low accuracy when collecting information.

[0005] To achieve the above-mentioned purpose, the present application provides an information verification method based on a screen recording video, which comprises:

[0006] obtaining a screen recording video when collecting user information;

[0007] converting the screen recording video into a video frame sequence sorted by time;

[0008] classifying each video frame in the video frame sequence using a pre-trained lightweight neural network to obtain a key video frame sequence;

[0009] performing operation scene recognition on the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence;

[0010] performing information verification on the screen recording video according to the operation scene sequence.

[0011] Optionally, the step of converting the screen recording video into a video frame sequence sorted by time comprises:

[0012] obtaining the video frame rate of the screen recording video and a preset target frame rate;

[0013] calculating the video frame interval to be extracted according to the video frame rate and the preset target frame rate;

[0014] extract a video frame set from the screen recording video according to the video frame interval, and sort the video frame set according to extraction time, to obtain a video frame sequence.

[0015] Optionally, the calculating the video frame interval to be extracted according to the video frame rate and the preset target frame rate comprises:

[0016] The video frame interval to be extracted is calculated by using the following formula:

[0017] i=int{float(f1 / f2)+1}

[0018] Wherein, the i is the video frame interval, the f1 is the video frame rate, the f2 is the target frame rate, the int is an integer function, and the float is a floating-point data type.

[0019] Optionally, the classifying each video frame in the video frame sequence by using the pre-trained lightweight neural network comprises:

[0020] Each video frame in the video frame sequence is input into the pre-trained lightweight neural network one by one.

[0021] The convolution layer in the lightweight neural network is used to convolve each video frame, to obtain a convolution feature map of each video frame.

[0022] The pooling layer in the lightweight neural network is used to pool the convolution feature map, to obtain a feature vector of each video frame.

[0023] A preset activation function is used to classify the feature vector of each video frame, to obtain a key video frame sequence.

[0024] Optionally, the operation scene recognition on the key video frame sequence comprises:

[0025] Text information in the key video frame is extracted from the key video frame in the key video frame sequence one by one.

[0026] Text segmentation is performed on the text information, and a text keyword is determined according to a result of the text segmentation.

[0027] The text keyword is matched with a pre-constructed operation scene set, to obtain an operation scene of the key video frame.

[0028] Optionally, the text information in the key video frame is extracted from the key video frame in the key video frame sequence one by one, comprising:

[0029] A text region boundary detection is performed on the key video frame, to obtain boundary coordinate points of a text region.

[0030] According to the boundary coordinate points, the key video frame is divided into a plurality of text regions;

[0031] A preset text recognition model is used for text recognition on the plurality of text regions, and text extraction is performed according to a text recognition result.

[0032] Optionally, the information verification on the screen recording video according to the operation scene sequence comprises:

[0033] A preset verification rule is obtained, the verification rule is parsed to obtain a rule expression of the verification rule;

[0034] The rule expression is used for verification on the operation scene sequence to obtain a verification result of the screen recording video.

[0035] To solve the above problems, the application further provides an information verification device based on a screen recording video, the device comprising:

[0036] A screen recording video acquisition module is configured to acquire a screen recording video during user information collection;

[0037] A video frame sequence conversion module is configured to convert the screen recording video into a video frame sequence sorted by time;

[0038] A key video frame sequence classification module is configured to classify each video frame in the video frame sequence by using a pre-trained lightweight neural network to obtain a key video frame sequence;

[0039] An operation scene identification module is configured to identify an operation scene of the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence;

[0040] A screen recording video verification module is configured to verify information of the screen recording video according to the operation scene sequence.

[0041] To solve the above problems, the application further provides an electronic device, the electronic device comprising:

[0042] At least one processor; and,

[0043] A memory in communication connection with the at least one processor; wherein,

[0044] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the information verification method based on a screen recording video.

[0045] To solve the above problems, the application further provides a computer readable storage medium, wherein at least one computer program is stored in the computer readable storage medium, and the at least one computer program is executed by a processor in an electronic device to implement the information verification method based on a screen recording video.

[0046] The embodiment of the application can obtain specific image information in the screen recording video by converting the screen recording video into a time-ordered video frame sequence and converting a video stream into a video frame image, can improve the accuracy of subsequent verification by classifying each video frame in the video frame sequence using a pre-trained lightweight neural network to obtain a key video frame sequence, and can improve the accuracy of user information filling by performing operation scene identification on the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence and verifying the screen recording video according to the operation scene sequence to determine whether the user violates the rules in the information filling process and whether the information filled by the user is correct. Therefore, the information verification method, device, electronic device and computer readable storage medium based on a screen recording video provided by the application can solve the problem of low accuracy in information collection. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 A flowchart of an information verification method based on a screen recording video provided by an embodiment of the application is shown in the figure.

[0048] Figure 2 A flowchart of video frame sequence conversion provided by an embodiment of the application is shown in the figure.

[0049] Figure 3 A flowchart of operation scene identification provided by an embodiment of the application is shown in the figure.

[0050] Figure 4 A function module diagram of an information verification device based on a screen recording video provided by an embodiment of the application is shown in the figure.

[0051] Figure 5 A structural diagram of an electronic device for implementing the information verification method based on a screen recording video provided by an embodiment of the application is shown in the figure.

[0052] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the application and not to limit the application.

[0054] The embodiment of the present application provides a method for verifying information based on a screen recording video. The execution subject of the method for verifying information based on a screen recording video includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the present application. In other words, the method for verifying information based on a screen recording video can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0055] Referring to Figure 1 FIG. 1 is a flowchart of a method for verifying information based on a screen recording video provided by an embodiment of the present application. In the embodiment, the method for verifying information based on a screen recording video includes the following steps S1-S5:

[0056] S1, obtaining a screen recording video during user information collection;

[0057] In the embodiment of the present application, the screen recording video is a screen recording during information filling by a user, and the screen recording can be initiated and ended by the user. Specifically, during information filling by the user, an embedded screen recording software on a user information collection platform can be called to perform screen recording.

[0058] In another optional embodiment of the present application, the user information collection platform is an enterprise platform requiring real information filling by a user, for example, a financial and insurance industry, a third-party credit investigation enterprise and the like, which needs to ensure the correctness of the user during user information collection.

[0059] S2, converting the screen recording video into a video frame sequence sorted by time;

[0060] In the embodiment of the present application, the video frame sequence is obtained by sorting single images in the screen recording video by time, so as to display the screen recording video in the form of images.

[0061] In detail, referring to Figure 2 FIG. 2, the step of converting the screen recording video into a video frame sequence sorted by time includes the following steps S21-S23:

[0062] S21, obtaining a video frame rate of the screen recording video and a preset target frame rate;

[0063] S22, calculate a video frame interval to be extracted according to the video frame rate and the preset target frame rate;

[0064] S23, extract a video frame set from the screen recording video according to the video frame interval, and sort the video frame set according to extraction time to obtain a video frame sequence.

[0065] Further, the calculating a video frame interval to be extracted according to the video frame rate and the preset target frame rate comprises:

[0066] The video frame interval to be extracted is calculated by using the following formula:

[0067] i=int{float(f1 / f2)+1}

[0068] Wherein, the i is a video frame interval, the f1 is a video frame rate, the f2 is a target frame rate, int is an integer function, and float is a floating-point data type.

[0069] In the embodiment of the application, the video frame rate of the screen recording video is the frame rate of the screen recording video image, for example, 25fps, that is, 25 frames of color code streams can be sent out per second, and the target frame rate is the required collection frame rate, for example, the preset target frame rate can be 10fps, and then the video frame interval to be extracted is calculated according to the video frame rate and the preset target frame rate.

[0070] In the embodiment of the application, the screen recording video is converted into a video frame sequence, the video stream is converted into a video frame image, the specific image information in the screen recording video can be obtained, and the video frame extraction is performed according to the calculated video frame interval, so that the content accuracy of the video frame of the target frame rate extracted from the screen recording video of the original frame rate is ensured.

[0071] S3, classify each video frame in the video frame sequence by using the pre-trained lightweight neural network to obtain a key video frame sequence.

[0072] In the embodiment of the application, the pre-trained lightweight neural network is MnasNet (a classical lightweight neural network), because the scene complexity for video frame classification is not high, the lightweight neural network is selected to reduce the model complexity and improve the operation efficiency, and specifically, the pre-trained lightweight neural network comprises a convolution layer, a pooling layer and a full connection layer.

[0073] In another optional embodiment of the application, the pre-trained lightweight neural network is obtained by recording a regular operation video by using a mainstream mobile phone model, extracting all video frames in the regular operation video, performing scene annotation on the video frames, performing neural network iterative training on the video frames after the scene annotation, and obtaining the pre-trained lightweight neural network.

[0074] In another optional embodiment of the present application, the key video frames include video frames with content such as jump page, login page, information filling page, and end screen recording page, and the key video frames can include key frames during information filling and fraud frames during cheating, and the video frames without content such as black screen and blank are removed, and then the key video frames are sorted based on the positions of the key video frames in the video frame sequence to obtain a key video frame sequence.

[0075] In detail, the classification of each video frame in the video frame sequence by using the pre-trained lightweight neural network includes:

[0076] Each video frame in the video frame sequence is input into the pre-trained lightweight neural network one by one;

[0077] The convolution layer in the lightweight neural network is used to perform convolution on each video frame to obtain a convolution feature map of each video frame;

[0078] The pooling layer in the lightweight neural network is used to perform pooling on the convolution feature map to obtain a feature vector of each video frame;

[0079] A preset activation function is used to classify the feature vector of each video frame to obtain a key video frame sequence.

[0080] In the embodiment of the present application, the activation function in the full connection layer is a sigmoid activation function, and the video frame category corresponding to the feature vector is calculated by using the activation function to obtain a key video frame, and then a key video frame sequence is obtained based on the position of each key video frame in the video frame sequence.

[0081] In the embodiment of the present application, the classification of each video frame in the video frame sequence by using the pre-trained lightweight neural network can improve the recognition efficiency of the video frame, and further improve the efficiency of subsequent information verification, delete useless video frames, and improve the accuracy of subsequent verification.

[0082] S4, operation scene recognition is performed on the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence;

[0083] In the embodiment of the present application, the operation scene recognition of the key video frame sequence is further to recognize the specific operation content of the key video frame, for example, the key video frame sequence is a page jump operation scene, a login operation scene, an end screen recording operation scene, and an operation scene of information fraud.

[0084] In detail, refer to Figure 3As shown, the operation scene identification on the key video frame sequence comprises steps S31-S33:

[0085] S31, text extraction is performed on the key video frames in the key video frame sequence one by one to obtain text information in the key video frames;

[0086] S32, text segmentation is performed on the text information, and a text keyword is determined according to a result of the text segmentation;

[0087] S33, the text keyword is matched with a pre-constructed operation scene set to obtain an operation scene of the key video frame.

[0088] In the embodiment of the application, the most frequently occurring segmented word in the text segmentation can be extracted as a text keyword, and the text keyword is matched with a pre-constructed operation scene set, wherein the pre-constructed operation scene set is a set of pre-set keywords and corresponding operation scenes, for example, if the text keyword is "login", the corresponding operation scene in the pre-constructed operation scene set is "login operation scene", and the operation scene corresponding to the video key frame is the login operation scene.

[0089] Further, the text extraction on the key video frames in the key video frame sequence one by one comprises:

[0090] boundary coordinate points of a text region are obtained by performing text region boundary detection on the key video frame;

[0091] the key video frame is divided into a plurality of text regions according to the boundary coordinate points;

[0092] text recognition is performed on the plurality of text regions by using a pre-set text recognition model, and text extraction is performed according to a result of the text recognition.

[0093] In the embodiment of the application, the pre-set text recognition model can be a pre-trained CRNN (Convolutional Recurrent Neural Network, convolutional recurrent neural network), which can solve the problem of text recognition based on an image sequence, and therefore, the text recognition model can be used to perform text recognition on the key video frame sequence.

[0094] In the embodiment of the application, by identifying the operation scene sequence corresponding to the key video frame, the operation process of the user when filling in the information can be obtained, and it is further determined whether the user complies with the information filling.

[0095] S5, information verification is performed on the screen recording video according to the operation scene sequence.

[0096] In the embodiment of the present application, the information verification is to determine whether the operation process of the user in the information filling process is compliant according to the operation scene sequence, and further determine whether the cheating behavior exists in the screen recording video.

[0097] In detail, the information verification of the screen recording video according to the operation scene sequence comprises:

[0098] A preset verification rule is obtained, the verification rule is parsed to obtain a rule expression of the verification rule;

[0099] The operation scene sequence is verified by using the rule expression to obtain a verification result of the screen recording video.

[0100] In the embodiment of the present application, the preset verification rule is a rule requirement that needs to be met by the operation scene sequence, and the verification rule is converted into, for example, the operation scene sequence is a page jump operation scene-log in operation scene-end screen recording operation scene, and there is no information filling process, and the screen recording video does not meet the verification rule, or the operation scene sequence is a jump operation scene-log in operation scene-information filling operation scene-log in operation scene-information filling operation scene-end screen recording operation scene, and the user has multiple intermittent log in behaviors, and the corresponding screen recording video does not meet the requirement.

[0101] In the embodiment of the present application, whether the user violates the rule in the information filling process can be determined through the operation scene sequence, so as to determine whether the information filled by the user is correct, and the correctness of the information filling of the user can be improved.

[0102] In the embodiment of the present application, the screen recording video is converted into a video frame sequence sorted by time, the video stream is converted into a video frame image, the specific image information in the screen recording video can be obtained, each video frame in the video frame sequence is classified by using the pre-trained lightweight neural network to obtain a key video frame sequence, the accuracy of subsequent verification can be improved, the key video frame sequence is subjected to operation scene identification to obtain an operation scene sequence corresponding to the key video frame sequence, the screen recording video is verified according to the operation scene sequence to determine whether the user violates the rule in the information filling process, so as to determine whether the information filled by the user is correct, and the correctness of the information filling of the user can be improved. Therefore, the information verification method based on the screen recording video can solve the problem of low correctness in information collection.

[0103] As shown in Figure 4 Fig. 1 is a functional module diagram of an information verification device based on a screen recording video provided by an embodiment of the present application.

[0104] The information verification device based on the screen recording video 100 can be installed in an electronic device. According to the functions implemented, the information verification device based on the screen recording video 100 can include a screen recording video acquisition module 101, a video frame sequence conversion module 102, a key video frame sequence classification module 103, an operation scene identification module 104, and a screen recording video verification module 105. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0105] In the present embodiment, the functions of each module / unit are as follows:

[0106] The screen recording video acquisition module 101 is configured to acquire a screen recording video during user information collection.

[0107] The video frame sequence conversion module 102 is configured to convert the screen recording video into a video frame sequence sorted by time.

[0108] The key video frame sequence classification module 103 is configured to classify each video frame in the video frame sequence using a pre-trained lightweight neural network to obtain a key video frame sequence.

[0109] The operation scene identification module 104 is configured to identify the operation scene of the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence.

[0110] The screen recording video verification module 105 is configured to verify the information of the screen recording video according to the operation scene sequence.

[0111] In detail, each module in the information verification device based on the screen recording video 100 in the present embodiment uses the same technical means as the information verification method based on the screen recording video described in the above Figures 1 to 3 , and can produce the same technical effects, which will not be described here.

[0112] As Figure 5 shown is a structural schematic diagram of an electronic device for implementing an information verification method based on a screen recording video according to an embodiment of the present application.

[0113] The electronic device 1 can include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as an information verification program based on a screen recording video.

[0114] The processor 10 may, in some embodiments, be composed of integrated circuits, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits of the same or different functions, including one or more combinations of central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connects various components of the electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (for example, executes the information verification program based on the screen recording video), and calls data stored in the memory 11 to perform various functions and process data of the electronic device.

[0115] The memory 11 includes at least one type of readable storage medium, including flash memories, mobile hard disks, multimedia cards, card-type memories (for example, SD or DX memories, etc.), magnetic memories, magnetic disks, optical disks, etc. The memory 11 may, in some embodiments, be an internal storage unit of the electronic device, for example, a mobile hard disk of the electronic device. The memory 11 may, in other embodiments, also be an external storage device of the electronic device, for example, a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 may include both an internal storage unit and an external storage device of the electronic device. The memory 11 can be used not only to store application software and various data installed in the electronic device, for example, the code of the information verification program based on the screen recording video, but also to temporarily store data that has been or will be output.

[0116] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0117] The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface can include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device and other electronic devices. The user interface can be a display, an input unit (such as a keyboard), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. The display can also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visualized user interface.

[0118] Only the electronic device with components is shown in the figure, and those skilled in the art can understand that the structure shown in the figure does not constitute a limitation on the electronic device, and can include fewer or more components than shown in the figure, or combine certain components, or different component arrangements.

[0119] For example, although not shown, the electronic device can also include a power supply (such as a battery) for powering each component. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so as to realize functions such as charge management, discharge management, and power consumption management through the power management device. The power supply can also include one or more direct current or alternating current power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0120] It should be understood that the embodiments are only for illustration and are not limited in the scope of the patent application by the structure.

[0121] The information verification program based on the screen recording video stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which, when running in the processor 10, can realize:

[0122] Obtaining a screen recording video during collection of user information;

[0123] Converting the screen recording video into a video frame sequence sorted by time;

[0124] Classifying each video frame in the video frame sequence using a pre-trained lightweight neural network to obtain a key video frame sequence;

[0125] Perform operation scene recognition on the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence.

[0126] Perform information verification on the screen recording video according to the operation scene sequence.

[0127] Specifically, the specific implementation method of the processor 10 on the above instructions can refer to the description of the related steps in the corresponding embodiment of the accompanying drawings, which will not be described here.

[0128] Further, the modules / units integrated in the electronic device 1 are implemented in the form of software function units and sold or used as independent products, which can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0129] The application also provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following steps when executed by a processor of an electronic device:

[0130] Obtain a screen recording video during collection of user information;

[0131] Convert the screen recording video into a video frame sequence sorted by time;

[0132] Classify each video frame in the video frame sequence by using a pre-trained lightweight neural network to obtain a key video frame sequence;

[0133] Perform operation scene recognition on the key video frame sequence to obtain an operation scene sequence corresponding to the key video frame sequence;

[0134] Perform information verification on the screen recording video according to the operation scene sequence.

[0135] In several embodiments provided in the application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiment described above is only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner.

[0136] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0137] In addition, each functional module in various embodiments of the application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional module.

[0138] It is obvious for those skilled in the art that the application is not limited to the details of the above exemplary embodiments, and the application can be implemented in other specific forms without departing from the spirit or essential characteristics of the application.

[0139] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the application. Any additional reference signs in the claims should not be considered as limiting the claims involved.

[0140] The blockchain referred to in the application is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm and other computer technologies. Blockchain, in essence, is a decentralized database, a series of data blocks associated using cryptography, each data block containing a batch of network transaction information for verifying the validity (anti-fake) of the information and generating the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0141] The embodiments of the application can acquire and process related data based on artificial intelligence technology. Artificial intelligence (AI) is the use of digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0142] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0143] Finally, it should be noted that the above examples are merely intended to illustrate the technical solutions of the present application and not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the present application.

Claims

1. A method for information verification based on screen-recorded video, characterized in that, The method includes: Screen recordings obtained during user information collection; The screen recording video is converted into a video frame sequence sorted by time. A pre-trained lightweight neural network is used to classify each video frame in the video frame sequence to obtain a key video frame sequence. The key video frame sequence is subjected to operation scene identification to obtain the operation scene sequence corresponding to the key video frame sequence; The screen recording video is verified based on the operation scenario sequence.

2. The information verification method based on screen recording video as described in claim 1, characterized in that, The step of converting the screen recording video into a time-ordered video frame sequence includes: Obtain the video frame rate and the preset target frame rate of the screen recording video; The interval of the video frames to be extracted is calculated based on the video frame rate and the preset target frame rate. Based on the video frame interval, a set of video frames is extracted from the screen recording video, and the set of video frames is sorted according to the extraction time to obtain a video frame sequence.

3. The information verification method based on screen recording video as described in claim 2, characterized in that, The step of calculating the video frame interval to be extracted based on the video frame rate and the preset target frame rate includes: The interval of the video frames to be extracted is calculated using the following formula: i = int{float(f1 / f2)+1} Where i is the video frame interval, f1 is the video frame rate, f2 is the target frame rate, int is the rounding function, and float is a floating-point data type.

4. The information verification method based on screen recording video as described in claim 1, characterized in that, The process of classifying each video frame in the video frame sequence using a pre-trained lightweight neural network includes: Each video frame in the video frame sequence is input one by one into the pre-trained lightweight neural network; Each video frame is convolved using the convolutional layers in the lightweight neural network to obtain a convolutional feature map for each video frame. The convolutional feature map is pooled using the pooling layer in the lightweight neural network to obtain the feature vector of each video frame; The feature vectors of each video frame are classified using a preset activation function to obtain a sequence of key video frames.

5. The information verification method based on screen recording video as described in claim 1, characterized in that, The operation scene identification of the key video frame sequence includes: Text is extracted from each key video frame in the key video frame sequence to obtain the text information in the key video frames. The text information is segmented into words, and text keywords are determined based on the results of the word segmentation. The text keywords are matched with a pre-constructed set of operation scenarios to obtain the operation scenario of the key video frame.

6. The information verification method based on screen recording video as described in claim 1, characterized in that, The step of extracting text from each key video frame in the key video frame sequence includes: Perform text region boundary detection on the key video frames to obtain the boundary coordinate points of the text regions; The key video frame is divided into multiple text regions based on the boundary coordinate points; The multiple text regions are used to perform text recognition using a preset text recognition model, and text is extracted based on the text recognition results.

7. The information verification method based on screen recording video as described in claim 1, characterized in that, The step of verifying information in the screen recording video according to the operation scenario sequence includes: Obtain the preset verification rules, parse the verification rules, and obtain the rule expression of the verification rules; The operation scenario sequence is validated using the rule expression to obtain the validation result of the screen recording video.

8. An information verification device based on screen recording video, characterized in that, The device includes: The screen recording video acquisition module is used to acquire screen recording videos during user information collection. The video frame sequence conversion module is used to convert the screen recording video into a video frame sequence ordered by time. The key video frame sequence classification module is used to classify each video frame in the video frame sequence using a pre-trained lightweight neural network to obtain the key video frame sequence. An operation scene recognition module is used to perform operation scene recognition on the key video frame sequence to obtain the operation scene sequence corresponding to the key video frame sequence. The screen recording video verification module is used to verify the information of the screen recording video according to the operation scenario sequence.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the information verification method based on screen recording video as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the information verification method based on screen recording video as described in any one of claims 1 to 7.

Images